100100 Ideas AI
Submit Tool

kubeshark

MCPOpen source

eBPF-powered Kubernetes network observability with TLS decryption, MCP integration for AI agents.

12kApache-2.0

eBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.

Pros

  • +Kernel-level eBPF capture with automatic TLS decryption without keys
  • +MCP server enables AI agents to query network data via natural language
  • +Supports multiple protocols (HTTP, gRPC, Redis, Kafka, DNS) with KFL query language
  • +Retrospective PCAP export and cloud storage integration

Cons

  • −Requires Kubernetes cluster and eBPF kernel support
  • −May have performance overhead on high-traffic clusters
  • −Complex setup for production with ingress configuration

Target audience: SREs and platform engineers who need deep Kubernetes network observability and want to integrate AI agents for incident response.

Related tools

Other open-source tools that share tags with kubeshark.

Unla

MCPMIT

Unla is a lightweight MCP gateway that converts existing APIs and MCP servers into MCP endpoints with zero code changes.

2.2k·MCP Servers·Open source